Who is this assistant for?

Your targets come from last year plus a percentage, and you never know whether they were reachable. You schedule shifts and purchasing by gut and some weeks you are overstaffed and others short. You have to build the year's budget and have nowhere to take sales from. You feel rain, long weekends or payday move your sales, but not by how much.

The month's target usually comes from last year's sales plus a percentage that feels right. Shifts, purchasing and the budget are planned with it, and when it is missed nobody knows whether the operation failed or the target did. This assistant has your AI, with the Universal Sales Forecast folder, prepare your restaurant's daily sales so the MASTERESTAURANT® engine builds two single-file interactive reports. The **3-month forecast** says how much you will sell each day, week and month with its 80% range, how far the written target is and how likely you are to reach it, and turns sales into shifts, dining-room areas, dishes and ingredients. The **12-month projection** gives next year's sales week by week for the budget, payroll and the commercial calendar. The error of both is measured blind on your own history and compared with a naive reference: the report tells you how much to believe it.

AI assistant · N5 Complete system

◆ Included in the annual plan🏦 Financial Intelligencev1.0.0 · 2026-10-08

📁 Needs an AI that builds files — Claude with Cowork or Claude Code📊 Works best with an AI that reads Excel or Sheets (Claude for Excel, ChatGPT, Copilot in Microsoft 365) · optional

Sales Forecast Tool Creator for Restaurants

With the Universal Sales Forecast folder, your AI builds the house's two reports from your real sales: the forecast for the next 3 months, day by day with its blind-measured range, and the 12-month projection of the following year for the budget. The engine in the folder computes the figures; your AI prepares the data and explains what they say.

Depth

13/24

Your data

Compatible AIs

Steps to use it

Depth of the resulttap a level to see what you get

◀ Put out today's fireRun the year ▶

🏛️

N5Complete system

Several chained pieces you install and operate over time, with their review cadence. It changes how the business runs, not one decision.

◆ This assistant 116 of the 169 published assistants are at this level

Is this for you?

What it does and what you get

The month's target usually comes from last year's sales plus a percentage that feels right.
Shifts, purchasing and the budget are planned with it, and when it is missed nobody knows whether the operation failed or the target did.
This assistant has your AI, with the Universal Sales Forecast folder, prepare your restaurant's daily sales so the MASTERESTAURANT® engine builds two single-file interactive reports.
The **3-month forecast** says how much you will sell each day, week and month with its 80% range, how far the written target is and how likely you are to reach it, and turns sales into shifts, dining-room areas, dishes and ingredients.
The **12-month projection** gives next year's sales week by week for the budget, payroll and the commercial calendar. The error of both is measured blind on your own history and compared with a naive reference: the report tells you how much to believe it.

What you end up with

The verdict on your data —how many days, since when, what is missing and whether it is enough—; your restaurant's folder built with the tool's templates; the 3-month forecast and the 12-month projection, each a single file that opens offline, built and reviewed by the engine's guardians; the verification with what stayed unverified; a five-line reading with the reports' figures; and the rhythm to run them again with its owner and its indicator.

EXAMPLE This is what you getAn example built with Tizón Norte, one of the house's fictional businesses.Not your data: your result is built with YOUR restaurant's.See the full example →

Sample result

Tizón NorteFictional northern Mexican grill in Mexico City: one location, 110 seats, 4 years open. Fictional house

The owner asked this: «I want to know how much we will sell from now to December and build the 2027 budget. I have three years of daily sales from the point of sale and the targets I set this year.»


Projected sales (P50, net of VAT)	$7.89 M
Likely range (8 out of 10)	$7.58 M – $8.20 M
Owner's written target	$8.51 M · −7.3% from the forecast
Probability of reaching the target	October 0% · November 9% · December 0%
Against the same dates of 2025	+1.6%
Weekly error measured blind	4.2% (naive reference 4.8% · target 7.9%) · 39 tests

Engine figures, built with the house's three years of sales. The report's recommendation: schedule purchases and shifts with P50 and keep the target as a commercial goal.

#	Action	Money at stake
1	Realistic targets at P50 and stretch at P75	$617k gap to the written target
2	Activate Monday, Tuesday and Wednesday with a measured test	$237k for every 10% more on those days
3	Prepare the highest weeks with shifts and production at P80	$85k cushion in the high weeks

The highest week is the one of 30 November ($659k); the lowest, the one of 5 October ($546k). The engine also measured that evening rain (18–23 h) takes about 5% off the house, with firm evidence.


2027 sales (P50, net of VAT)	$30.90 M
80% range	$29.58 M – $32.28 M
Against 2026	+5.9% nominal · +2.0% real
Strongest week	the one of 29 November · $692k
Strongest and weakest month	December $2.93 M · February $2.09 M
2027 ticket	$567 (+3.4%)

Illustrative example generated with a fictional restaurant. Not a promise of results, not a client case.

This is 3 of 4 parts. Behind the wall are **both full reports —the 3-month forecast and the 2027 projection—**, **the action plan with its five actions** and **the dishes and ingredients the forecast sales call for**.

See the full example — free account

Works with these AIs

Claude — the best for this assistant Best for this one: with Cowork or Claude Code it reads your sales export, builds the restaurant folder, runs the engine until LISTO and leaves both reports on your machine.

How to use it

Export each location's daily sales for the last 2 or 3 years, net of taxes (if your system gives them with taxes, have the rate at hand).

Fill in your city, locations, monthly sales, ticket and goal in My Restaurant.

Download the Universal Sales Forecast Kit from this page and unzip it; open the two reports in ejemplo/salida/ to see what you will get.

Paste this assistant into your AI together with the folder and your sales. Get the verdict on the data and decide whether to go on.

With an AI that runs code (Claude with Cowork or Claude Code) you get both reports ready; with another, double-click «Armar mis reportes» with Python 3 and Node installed.

Which of your data it uses

of 24

This assistant works with 13 of the 24 fields in «My Restaurant», among them Restaurant name, Business type and City and country. It does not ask out of curiosity: these are what make the answer speak about YOUR scale instead of an industry average — the same calculation on a business of another size returns a number you cannot decide with. You fill them once and they apply across the library, so the second assistant you open already starts with them in place. Whatever you leave blank, the assistant asks for one thing at a time instead of inventing it, and says so before answering, so you know what it is working from.

Restaurant nameBusiness typeCity and countryNumber of locationsYears in businessAverage monthly salesAverage check (with currency)Approximate food cost (%)Approximate labor cost (%)Strong and slow daypartsActive sales channelsBest-selling dishesMain goal this year